© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30423
    Prev
    Next
    INDEX
    Explanations

    mechanical process or malfunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     \
    0.33
    %),
    0.30
    );\
    0.29
    %)
    0.29
     It
    0.28
     hä
    0.28
    %,
    0.28
    .),
    0.27
    >,
    0.27
     He
    0.26
    POSITIVE LOGITS
    ни
    0.33
    ي
    0.32
    برای
    0.32
     Grafton
    0.31
    К
    0.31
    ک
    0.30
    ográf
    0.30
    ت
    0.30
    i
    0.30
    ᱴ
    0.30
    Activations Density 0.005%

    No Known Activations